Representative-based metric learning for classification and few-shot object detection

A system comprising:

• a processor to implement a neural network architecture comprising computer-executable instructions that cause the processor to:
• jointly learn a feature extractor model, a common embedding space for a resulting feature space, and a set of parameters for each one of a set of mixture models, wherein one mixture model is associated with one class of objects within a set of object categories;
• add new mixture models to the set of mixture models to support novel categories based on a set of example embedding vectors computed for each one of the novel categories;
• detect in images a plurality of boxes with associated labels and corresponding confidence scores, wherein the boxes correspond to image regions comprising objects of both known categories and the novel categories;
• and
• given a query image, execute an instruction based on the common embedding space and the set of mixture models, the instruction comprising identifying objects from the known categories and the novel categories in the query image.

A computer program product for detecting objects in images comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to:

• jointly learn a feature extractor model, a common embedding space for a resulting feature space, and a set of parameters for each one of a set of mixture models, wherein one mixture model is associated with one class of objects within a set of object categories;
• add new mixture models to the set of mixture models to support novel categories based on a set of example embedding vectors computed for each one of the novel categories;
• detect in images a plurality of boxes with associated labels and corresponding confidence scores, wherein the boxes correspond to image regions comprising objects of both known categories and the novel categories;
• and
• given a query image, execute an instruction based on the common embedding space and the set of mixture models, the instruction comprising identifying objects from the known categories and the novel categories in the query image.